© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 226904
    Prev
    Next
    INDEX
    Explanations

    foreign language texts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     miracle
    0.45
     salvage
    0.45
    镓
    0.44
     tume
    0.44
     шесть
    0.43
    теле
    0.42
    фона
    0.41
     исправ
    0.40
     электрон
    0.40
     kosher
    0.39
    POSITIVE LOGITS
    ك
    0.54
     Eq
    0.51
    邁
    0.49
     الدولة
    0.45
    中國
    0.45
    യായിരുന്നു
    0.43
     oppress
    0.43
    اصيل
    0.42
     هذا
    0.42
     لدينا
    0.42
    Activations Density 0.002%

    No Known Activations